Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add agentsope/SkillAlchemy --skill agentsop-module-shape-selectiongit clone --depth 1 https://github.com/agentsope/SkillAlchemyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/agentsope/skillalchemy/agentsop-module-shape-selection)<a href="https://agentmods.dev/skills/agentsope/skillalchemy/agentsop-module-shape-selection"><img src="https://agentmods.dev/badge/skills/agentsope/skillalchemy/agentsop-module-shape-selection/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/agentsope/skillalchemy/agentsop-module-shape-selection"><img src="https://agentmods.dev/badge/skills/agentsope/skillalchemy/agentsop-module-shape-selection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 322 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00174 | $0.04567 |
| Opus 5.5 | $0.00070 | $0.01827 |
| Sonnet 5.5 | $0.00035 | $0.00913 |
| Haiku 4.5 | $0.00017 | $0.00457 |
Grade A, and why
agentsop-module-shape-selection scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
M2 — Module-Shape Selection (CoT / ReAct / PoT / Predict)
"Pick the lowest-power Module that works. Default to ChainOfThought." — DSPy docs [dspy.ai/learn/programming/modules/]
This overlay sharpens that line into a rubric: the default is not a law. The shape is a function of the task structure, and CoT is only one of four answers.
This is an enhancement overlay. It assumes the [[dspy]] library skill is loaded
(it provides dspy.Predict, dspy.ChainOfThought, dspy.ReAct,
dspy.ProgramOfThought APIs and install). This file adds only the decision the lib
skill leaves implicit. Cross-link: [[dspy]], and the optimizer SOP [[agentsop-dspy]].
1. 何时激活 (When to activate)
Activate the instant you are about to add or wrap an LM-calling step:
| Trigger | Signal |
|---|---|
| New node | A LangGraph/CrewAI node body, or a forward() line, is about to call an LM |
New dspy.<Module>(Sig) |
You are typing dspy.ChainOfThought(...) on reflex — stop and run the rubric |
| Refactor | An existing Predict "feels weak" or a ChainOfThought "feels wasteful" |
| Pipeline growth | A multi-stage program adds a stage; each stage needs its own shape decision |
| Tool appears | A function/API/search/calculator is now available to the step |
Do NOT activate when:
- The work is a one-shot prompt — just call the LM; shape ceremony has no payoff.
- You are choosing the optimizer / teleprompter (MIPROv2, GEPA, BootstrapFewShot) — that is the [[agentsop-dspy]] workflow, a later stage. Shape comes first, optimizer second.
- The step is non-LM control flow (a
if, a DB read, a deterministic transform).
Shape selection is upstream of optimization. You pick the shape in Stage 1 (Programming) of the dspy SOP, before any metric or compile [dspy.ai/learn/].
2. 核心心智模型 (Core mental model)
Reasoning shape is chosen by task structure, not by defaulting to CoT.
The lib skill shows four modules side by side and a "Best Practices" note that says
"Start with Predict, add ChainOfThought if needed" [~/.claude/skills/dspy Best
Practices §1]. In practice that collapses into a CoT-everywhere reflex, because
"if needed" is never operationalized. This overlay operationalizes it.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 326 lines · 174 tokens per session scan A 7bab8946f2bb
agentsop-module-shape-selection is a skill published in the GitHub repository agentsope/SkillAlchemy (445 stars, last pushed 14d ago), licensed MIT. It adds 174 tokens to every session and 4,567 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
prompt-evaluation-runner
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
prompt-perturb
Inject outside-angle prompts from creativity-technique catalogs when work is stuck in the same moves.
prompt-refine
Silently restructures the user's natural-language prompt into the format the model CURRENTLY running this skill handles best, then answers. On activation it identifies which model family is executing it (Claude, GPT, Gemini, Llama, DeepSeek, Mistral, Qwen, Grok, Perplexity, Kimi, GLM, Command, Nova, or Phi) and loads…
build-dotnet-agent-service
Build a local-first F# or C# Semantic Kernel agent service with explicit tools, model capability checks, evaluation fixtures, and draft-before-write promotion.
prompt-decorators
Activates a structured decorator framework that modifies how Claude reasons, responds, and formats output. Trigger this skill whenever a prompt contains one or more markers prefixed with +++, such as +++Reasoning, +++StepByStep, +++Tone(style=formal), or any other +++ marker, regardless of what follows in the prompt.…
vibe-creating-prompt
Judges whether a user's input suits the Vibe Creating style of video-prompt writing, and when it does, distills single-scene prompts, multi-shot descriptions, emotional imagery, or mixed input into prompts that are easier for a video model to generate from — while preserving any user-specified dialogue, voiceover…